How to use embaas/sentence-transformers-multilingual-e5-base with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("embaas/sentence-transformers-multilingual-e5-base") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]
Thank you for these embeddings! I've tried many of the popular ones and nothing worked for a low to medium resource language. These work great with semantic search, and can sometimes out-compete OpenAI's ada-002. Keep the good work :)
· Sign up or log in to comment
